CN117334051A - Highway vehicle track reconstruction method and system - Google Patents
Highway vehicle track reconstruction method and system Download PDFInfo
- Publication number
- CN117334051A CN117334051A CN202311401161.7A CN202311401161A CN117334051A CN 117334051 A CN117334051 A CN 117334051A CN 202311401161 A CN202311401161 A CN 202311401161A CN 117334051 A CN117334051 A CN 117334051A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- track
- time
- representing
- internet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000000903 blocking effect Effects 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 claims abstract description 20
- 238000009499 grossing Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims abstract description 10
- 238000011144 upstream manufacturing Methods 0.000 claims description 18
- 238000010606 normalization Methods 0.000 claims description 9
- 230000035939 shock Effects 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims 2
- 230000000694 effects Effects 0.000 description 3
- 230000035699 permeability Effects 0.000 description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 1
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method for reconstructing a track of a highway vehicle, which comprises the following steps: inputting fixed detection data and network connection data, and estimating the space position of a vehicle in a road section and the traffic speed of running under time; the fixed detection data carries out candidate track calculation on the detected non-network-connected vehicles, and the network-connected vehicle track is taken as a reference; the invention fully fuses sparse network vehicle-connected data and fixed detector data, considers different characteristics of traffic flow in traffic flow blocking and free flow states, complements a space-time velocity matrix by a self-adaptive smoothing method, takes the space-time velocity matrix generated by a macroscopic model as constraint, combines the vehicle track generated by a following model, and realizes full-sample high-resolution track reconstruction of robustness of different data scenes.
Description
Technical Field
The invention relates to a track reconstruction method and system for a highway vehicle, in particular to the technical field of track reconstruction.
Background
The vehicle track reconstruction means that the vehicle running track is obtained through processing and analyzing vehicle running data, the vehicle track data is basic data of road traffic design, optimization, control and management work in each stage, and for vehicles running at high speed, the track of the vehicle can be obtained through recording the track of the vehicle through GPS, vehicle-mounted radar and video equipment; because the vehicle is blocked, unobstructed and detained on the expressway and the motion parameters of the vehicle track are not consistent, track reconstruction is needed before track data is used, the existing method based on the traffic macro-micro model is poor in macro-level consideration, only the characteristics of blocking flow propagation are applied to traffic speed estimation, but in practice, the propagation of traffic flow is influenced by blocking flow and free flow characteristics at the same time, only the characteristics of blocking flow are considered to have a certain negative effect on the vehicle track reconstruction precision, most of high-resolution vehicle track reconstruction methods depend on the traffic micro model, only a single data source, namely network vehicle connection data, is considered by the method based on the traffic micro model, the data of the existing fixed detector are ignored, and the reconstruction precision is required to be further improved.
Disclosure of Invention
The invention aims to: an object is to propose a method for reconstructing the trajectory of a highway vehicle, so as to solve the above-mentioned problems existing in the prior art;
the technical scheme is as follows: a highway vehicle track reconstruction method, comprising:
step 1, inputting fixed detection data and network connection data, and estimating the space position of a vehicle in a road section and the traffic speed of running under time;
step 2, fixed detection data carries out candidate track calculation on the detected non-network-connected vehicles, and the network-connected vehicle track is taken as a reference;
and step 3, carrying out weighting method fusion on the non-networked vehicles to obtain two candidate tracks, and obtaining the reconstruction track of each vehicle.
In a further embodiment, the step 1, the fixed detector data includes a detection record unique identification, a vehicle location speed, and a vehicle elapsed time;
the unique identification of the detection record is used for carrying out detection record on vehicles running in the road section;
the vehicle location speed is used for setting the fixed point position of the detected and recorded vehicle;
the vehicle elapsed time; calculating a time stamp of the vehicle passing through the detector according to the fixed point position;
the network connection data comprise a vehicle unique identifier, a time stamp, vehicle coordinates and vehicle speed;
the unique identification of the vehicle is used for tracking and marking the network-connected vehicle;
time stamp, time of network connection passing through unique identification position;
and directly uploading the vehicle coordinates and the vehicle speed of the internet-connected vehicle according to the tracking mark and the time stamp.
In a further embodiment, estimating the space position of the vehicle in the road section and the speed of running under time by a self-adaptive smoothing method on the basis of the fixed detection data and the network connection data, complementing a space-time speed matrix, and performing inclined setting on a smoothing core in the self-adaptive smoothing method according to the characteristics of traffic jam flow and free flow; the expression is as follows:
wherein x is i 、t i 、v i (i=1,., n) are the known location, time, and traffic speed under the corresponding space-time, respectively; (x, t) represents a position in space-time; phi represents the smooth core of the image,representing the normalization factor; v (V) free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; c free Representing the speed of disturbance propagation in the traffic free stream; c cong Representing the speed of disturbance propagation in traffic choked flow.
In a further embodiment, parameters of the smoothing kernel and normalization factor are calculated from the slope setting of the smoothing kernel as follows:
wherein x is i 、t i 、v i (i=1,., n) are the known location, time, and traffic speed under the corresponding space-time, respectively; (x, t) represents a position in space-time; phi represents the smooth core of the image,representing the normalization factor; sigma represents the smoothed width in the spatial coordinates; τ represents the smoothed width in time coordinates.
In a further embodiment, the free flow and the blocked flow characteristics are weighted based on a weight W, the specific expression is as follows:
wherein V is free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; v (V) thr Representing a threshold between free flow and blocked flow; deltaV represents the transition width between free and choked flow.
In a further embodiment, the weight based W, V free And V cong The traffic speed in time and space under estimation is expressed as follows:
V refer (x,t)=w(x,t)V cong (x,t)+[1-w(x,t)]V free (x,t)
wherein V is refer Representing traffic speed; v (V) free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; w represents the shock velocity; (x, t) represents a position in space-time.
In a further embodiment, step 2 is performed according to the adjacent upstream internet-enabled vehicle track Y in the internet-enabled vehicle track set Y i And downstream net train track Y i+1 With a reconstruction interval therebetweenN represents the number of non-networked vehicle tracks that need to be reconstructed within this interval.
According to the following model, the track of the rear vehicle n and the track of the front vehicle n-1 are set to be consistent, and the time lag tau is provided n And a spatial lag delta n The specific calculation mode is as follows:
where w represents shock velocity, k j Representing occlusion density;
for each reconstruction intervalEach non-network vehicle in the vehicle is respectively connected with the upstream network vehicle track Y based on the following model i And downstream net train track Y i+1 For reference, an nth non-networked vehicle of the tracks to be reconstructed in two adjacent networked vehicle tracks of non-networked vehicle N (n=1, 2,.., N) is generated, and a candidate track generated according to an upstream networked vehicle track is denoted by->And an nth non-networked vehicle of the tracks to be reconstructed in the two adjacent networked vehicle tracks, and generating a candidate track according to the downstream networked vehicle trackThe expression is as follows:
(when n=1,/is>)
(when n=n->)
Where τ represents the time interval; delta represents the spatial separation; t represents the position in space-time.
In a further embodiment, the step 3 uses the traffic speed calculated in the step 1 as a constraint to solve the candidate track weight of each non-internet-connected vehicleAnd->The specific expression is as follows:
wherein T represents the time interval of uploading the internet-connected vehicle data;the speed of the vehicle represented by the reconstructed track of the non-internet-connected vehicle n at the time t is represented; />Representing that the space-time velocity matrix estimated in step S1 is at (t +.>) Traffic speed values at space-time locations; />The position of the vehicle represented by the reconstruction track of the non-internet-connected vehicle n at the time t is represented; />The position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to an upstream internet-connected vehicle track at the time t is represented; />Representing the position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to the downstream internet-connected vehicle track at the time t; />Candidate trajectory +.representing non-networked vehicle n>Weights of (2); s.t. represents constraint conditions; />Representing vehicles represented by candidate tracks generated by non-networked vehicle n according to upstream networked vehicle trackThe position of the vehicle at the time t;
fusing candidate tracks of the non-internet-connected vehicle n according to the weight calculation resultAnd->Outputting the vehicle track reconstruction result +.>
Wherein,representing a reconstruction track of the non-internet-connected vehicle n; />The position of the vehicle represented by the candidate track generated by the non-internet-connected vehicle n according to the upstream internet-connected vehicle track at the time t is represented.
The beneficial effects are that: the invention provides a method and a system for reconstructing a vehicle track of a highway, which fully fuses sparse network vehicle connection data and fixed detector data, considers different characteristics of traffic flow in traffic flow blocking and free flow states, complements a space-time velocity matrix by a self-adaptive smoothing method, takes the space-time velocity matrix generated by a macroscopic model as constraint and combines the vehicle track generated by a following model, so that full-sample high-resolution track reconstruction of robustness of different data scenes is realized, in the macroscopic traffic model, the characteristics of free flow and blocking flow propagation are considered at the same time, the method and the system are applied to traffic speed estimation, speed estimation structural errors caused by only considering blocking are reduced, and a reliable scheme is provided for robust high-resolution track reconstruction.
Drawings
FIG. 1 is a schematic flow chart of the treatment method of the present invention.
Fig. 2 is a schematic diagram of a flow of fixed detection data and internet protocol vehicles according to the present invention.
Detailed Description
The applicant believes that the existing method only uses the characteristic of blocking flow propagation in traffic speed estimation, but in practice, the propagation of traffic flow is influenced by both the blocking flow and free flow characteristics, and only considering the characteristic of blocking flow can have a certain negative effect on vehicle track reconstruction accuracy, so that it is necessary to reduce the structural error of speed estimation caused by blocking.
In order to solve the problems in the prior art, the invention realizes the aim of simultaneously considering the characteristics of free flow and blocking flow propagation by a method for reconstructing the track of the highway vehicle, and applies the method to traffic speed estimation to reduce the structural error of speed estimation caused by only considering blocking,
the present invention will be described in more detail with reference to the following examples and the accompanying drawings.
In the present application, we propose a method for reconstructing the track of a highway vehicle, comprising the steps of:
step 1, inputting fixed detection data and network connection data, and estimating the space position of a vehicle in a road section and the traffic speed of running under time; the fixed detector data includes a detection record unique identifier, a vehicle location speed, and a vehicle elapsed time;
the unique identification of the detection record is used for carrying out detection record on vehicles running in the road section;
the vehicle location speed is used for setting the fixed point position of the detected and recorded vehicle;
the vehicle elapsed time; calculating a time stamp of the vehicle passing through the detector according to the fixed point position;
the network connection data comprise a vehicle unique identifier, a time stamp, vehicle coordinates and vehicle speed;
the unique identification of the vehicle is used for tracking and marking the network-connected vehicle;
time stamp, time of network connection passing through unique identification position;
and directly uploading the vehicle coordinates and the vehicle speed of the internet-connected vehicle according to the tracking mark and the time stamp.
Estimating the space position of a vehicle in a road section and the running speed under time by a self-adaptive smoothing method on the basis of the fixed detection data and the network vehicle connection data, complementing a space-time speed matrix, and obliquely setting a smoothing core in the self-adaptive smoothing method according to the characteristics of traffic jam flow and free flow; the expression is as follows:
wherein x is i 、t i 、v i (i=1,., n) are the known location, time, and traffic speed under the corresponding space-time, respectively; (x, t) represents a position in space-time; phi represents the smooth core of the image,representing the normalization factor; v (V) free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; c free Representing the speed of disturbance propagation in the traffic free stream; c cong Representing the speed of disturbance propagation in traffic choked flow.
Parameters of the smoothing kernel and the normalization factor are calculated according to the inclination setting of the smoothing kernel, and the expression is as follows:
wherein x is i 、t i 、v i (i=1,., n) are the known location, time, and traffic speed under the corresponding space-time, respectivelyThe method comprises the steps of carrying out a first treatment on the surface of the (x, t) represents a position in space-time; phi represents the smooth core of the image,representing the normalization factor; sigma represents the smoothed width in the spatial coordinates; τ represents the smoothed width in time coordinates.
The free flow and the blocked flow characteristics are weighted based on the weight W, and the specific expression is as follows:
wherein V is free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; v (V) thr Representing a threshold between free flow and blocked flow; deltaV represents the transition width between free and choked flow.
Based on weight W, V free And V cong The traffic speed in time and space under estimation is expressed as follows:
V refer (x,t)=w(x,t)V cong (x,t)+[1-w(x,t)]V free (x,t)
wherein V is refer Representing traffic speed; v (V) free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; w represents the shock velocity; (x, t) represents a position in space-time.
Step 2, fixed detection data carries out candidate track calculation on the detected non-network-connected vehicles, and the network-connected vehicle track is taken as a reference; according to adjacent upstream network-connected vehicle track Y in network-connected vehicle track set Y i And downstream net train track Y i+1 With a reconstruction interval therebetweenN represents the number of non-networked vehicle tracks that need to be reconstructed within this interval.
According to the following model, the track of the rear vehicle n and the track of the front vehicle n-1 are set to be consistent, and the time lag tau is provided n And a spatial lag delta n The specific calculation mode is as follows:
where w represents shock velocity, k j Representing occlusion density;
for each reconstruction intervalEach non-network vehicle in the vehicle is respectively connected with the upstream network vehicle track Y based on the following model i And downstream net train track Y i+1 For reference, an nth non-networked vehicle of the tracks to be reconstructed in two adjacent networked vehicle tracks of non-networked vehicle N (n=1, 2,.., N) is generated, and a candidate track generated according to an upstream networked vehicle track is denoted by->And an nth non-networked vehicle of the tracks to be reconstructed in the two adjacent networked vehicle tracks, and generating a candidate track according to the downstream networked vehicle trackThe expression is as follows:
(when n=1,/is>)
(when n=n->)
Where τ represents the time interval; delta represents the spatial separation; t represents the position in space-time.
Step 3, carrying out weighting method fusion on the non-network-connected vehicles to obtain two candidate tracks, and obtaining each trackAnd (3) solving candidate track weights of each non-networked vehicle by taking the traffic speed calculated in the step (1) as a constraint on the reconstructed track of the vehicleAnd->The specific expression is as follows:
wherein T represents the time interval of uploading the internet-connected vehicle data;the speed of the vehicle represented by the reconstructed track of the non-internet-connected vehicle n at the time t is represented; />Representing that the space-time velocity matrix estimated in step S1 is at (t +.>) Traffic speed values at space-time locations; />The position of the vehicle represented by the reconstruction track of the non-internet-connected vehicle n at the time t is represented;the position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to an upstream internet-connected vehicle track at the time t is represented;representing the position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to the downstream internet-connected vehicle track at the time t;candidate trajectory +.representing non-networked vehicle n>Weights of (2); s.t. represents constraint conditions; />The position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to an upstream internet-connected vehicle track at the time t is represented;
fusing candidate tracks of the non-internet-connected vehicle n according to the weight calculation resultAnd->Outputting the vehicle track reconstruction result +.>
Wherein,representing a reconstruction track of the non-internet-connected vehicle n; />The position of the vehicle represented by the candidate track generated by the non-internet-connected vehicle n according to the upstream internet-connected vehicle track at the time t is represented.
The invention is compared with the vehicle track reconstruction in the existing mode, and the following data are obtained:
wherein MAPE represents the mean absolute percentage error; RMSE represents root mean square error; MAE represents the mean absolute error; compared with the prior art, the track reconstruction method provided by the invention has higher precision when solving the problem of vehicle track reconstruction under extremely low network vehicle connection permeability, realizes 44.6% improvement under 5% permeability and improves the reconstruction effect under 10% and 15% permeability, so that the track reconstruction method has certain robustness for scenes with scarce network vehicle connection data, can be compatible with vehicle track reconstruction requirements under different data scenes, and has important significance in application of real scenes.
As described above, although the present invention has been shown and described with reference to certain preferred embodiments, it is not to be construed as limiting the invention itself. Various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (8)
1. A method for reconstructing a track of a highway vehicle, comprising:
step 1, inputting fixed detection data and network connection data, and estimating the space position of a vehicle in a road section and the traffic speed of running under time;
step 2, fixed detection data carries out candidate track calculation on the detected non-network-connected vehicles, and the network-connected vehicle track is taken as a reference;
and step 3, carrying out weighting method fusion on the non-networked vehicles to obtain two candidate tracks, and obtaining the reconstruction track of each vehicle.
2. The method for reconstructing a track of a highway vehicle according to claim 1, wherein said step 1, said fixed detector data comprises detecting a record unique identifier, a vehicle location speed and a vehicle elapsed time;
the unique identification of the detection record is used for carrying out detection record on vehicles running in the road section;
the vehicle location speed is used for setting the fixed point position of the detected and recorded vehicle;
calculating the time stamp of the vehicle passing detector according to the vehicle passing time and the fixed point position;
the network connection data comprise a vehicle unique identifier, a time stamp, vehicle coordinates and vehicle speed;
the unique identification of the vehicle is used for tracking and marking the network-connected vehicle;
time stamp, time of network connection passing through unique identification position;
and directly uploading the vehicle coordinates and the vehicle speed of the internet-connected vehicle according to the tracking mark and the time stamp.
3. The method for reconstructing the track of the vehicle on the highway according to claim 1, wherein the space position of the vehicle in the road section and the speed of the vehicle running in time are estimated by an adaptive smoothing method based on the fixed detection data and the network connection data, a space-time speed matrix is complemented, and the smooth core in the adaptive smoothing method is obliquely arranged according to the characteristics of traffic jam flow and free flow; the expression is as follows:
wherein x is i 、t i 、v i (i=1,., n) are the known location, time, and traffic speed under the corresponding space-time, respectively; (x, t) represents a position in space-time; phi represents the smooth core of the image,representing the normalization factor; v (V) free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; c (C) free Representing the speed of disturbance propagation in the traffic free stream; c cong Representing the speed of disturbance propagation in traffic choked flow.
4. The method for reconstructing a track of a highway vehicle according to claim 1, wherein parameters of the smoothing kernel and the normalization factor are calculated according to an inclination setting of the smoothing kernel, expressed as follows:
wherein x is i 、t i 、v i (i=1,., n) are the known location, time, and traffic speed under the corresponding space-time, respectively; (x, t) represents a position in space-time; phi represents the smooth core of the image,representing the normalization factor; sigma represents the smoothed width in the spatial coordinates; />Representing the smoothed width in time coordinates.
5. The method for reconstructing the track of a highway vehicle according to claim 1, wherein the characteristics of free flow and blocked flow are weighted based on a weight W, and the specific expression is as follows:
wherein V is free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; v (V) thr Representing a threshold between free flow and blocked flow; deltaV represents the transition width between free and choked flow.
6. The method for reconstructing a track of a highway vehicle according to claim 1, wherein said method is based on weight W, V free And V cong The traffic speed in time and space under estimation is expressed as follows:
V refer (x,t)=w(x,t)V cong (x,t)+[1-w(x,t)]V free (x,t)
wherein V is refer Representing traffic speed; v (V) free Representing a free flow threshold; v (V) cong Representing a blocking flow threshold; ω represents shock velocity; (x, t) represents a position in space-time.
7. The method for reconstructing the track of a highway vehicle according to claim 1, wherein said step 2 is performed according to the adjacent upstream network-connected track Y in the track set Y of the network-connected track i And downstream net train track Y i+1 With a reconstruction interval therebetweenN represents the number of non-networked vehicle tracks that need to be reconstructed within this interval.
According to the following model, the track of the rear vehicle n and the track of the front vehicle n-1 are set to be consistent, and the time delay is providedAnd a spatial lag delta n The specific calculation mode is as follows:
wherein ω represents shock velocity, k j Representing occlusion density;
for each reconstruction intervalEach non-network vehicle in the vehicle is respectively connected with the upstream network vehicle track Y based on the following model i And downstream net train track Y i+1 For reference, an nth non-networked vehicle of the tracks to be reconstructed in two adjacent networked vehicle tracks of non-networked vehicle N (n=1, 2,.., N) is generated, and a candidate track generated according to an upstream networked vehicle track is denoted by->And the nth non-networked vehicle of the tracks to be reconstructed in the two adjacent networked vehicle tracks, and candidate tracks generated according to the downstream networked vehicle tracks are +.>The expression is as follows:
(when n=1,/is>)
(when n=n->)
Where τ represents the time interval; delta represents the spatial separation; t represents the position in space-time.
8. The method for reconstructing the track of the vehicle on the highway according to claim 1, wherein said step 3 is implemented to solve the candidate track weight of each non-networked vehicle using the traffic speed calculated in step 1 as a constraintAnd->The specific expression is as follows:
wherein T represents the time interval of uploading the internet-connected vehicle data;vehicle represented by reconstructed track representing non-networked vehicle nThe speed of the vehicle at time t; />Representing that the space-time velocity matrix estimated in step S1 is +.>Traffic speed values at space-time locations; />The position of the vehicle represented by the reconstruction track of the non-internet-connected vehicle n at the time t is represented; />The position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to an upstream internet-connected vehicle track at the time t is represented; />Representing the position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to the downstream internet-connected vehicle track at the time t; />Candidate trajectory +.representing non-networked vehicle n>Weights of (2); s.t. represents constraint conditions; />The position of a vehicle represented by a candidate track generated by the non-internet-connected vehicle n according to an upstream internet-connected vehicle track at the time t is represented;
fusing candidate tracks of the non-internet-connected vehicle n according to the weight calculation resultAnd->Outputting a vehicle track reconstruction result
Wherein,representing a reconstruction track of the non-internet-connected vehicle n; />The position of the vehicle represented by the candidate track generated by the non-internet-connected vehicle n according to the upstream internet-connected vehicle track at the time t is represented.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311401161.7A CN117334051B (en) | 2023-10-26 | Highway vehicle track reconstruction method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202311401161.7A CN117334051B (en) | 2023-10-26 | Highway vehicle track reconstruction method and system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117334051A true CN117334051A (en) | 2024-01-02 |
CN117334051B CN117334051B (en) | 2024-05-10 |
Family
ID=
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006125291A1 (en) * | 2005-05-25 | 2006-11-30 | Hiroyuki Takada | System and method for estimating travel times of a traffic probe |
CN109064741A (en) * | 2018-08-01 | 2018-12-21 | 北京航空航天大学 | The method of trunk road vehicle running track reconstruct based on multisource data fusion |
CN109348423A (en) * | 2018-11-02 | 2019-02-15 | 同济大学 | A kind of arterial road coordinate control optimization method based on sample path data |
CN109376952A (en) * | 2018-11-21 | 2019-02-22 | 深圳大学 | A kind of crowdsourcing logistics distribution paths planning method and system based on track big data |
EP3627472A1 (en) * | 2018-09-19 | 2020-03-25 | Deutsche Telekom AG | Method and assembly for automated local control of multi-modal urban traffic flows |
US20220169281A1 (en) * | 2020-11-30 | 2022-06-02 | Automotive Research & Testing Center | Trajectory determination method for a vehicle |
CN115311854A (en) * | 2022-07-22 | 2022-11-08 | 东南大学 | Vehicle space-time trajectory reconstruction method based on data fusion |
CN116257797A (en) * | 2022-12-08 | 2023-06-13 | 江苏中路交通发展有限公司 | Single trip track identification method of motor vehicle based on Gaussian mixture model |
CN117473741A (en) * | 2023-10-31 | 2024-01-30 | 东南大学 | Full-sample high-resolution vehicle track robust reconstruction method, device and medium |
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2006125291A1 (en) * | 2005-05-25 | 2006-11-30 | Hiroyuki Takada | System and method for estimating travel times of a traffic probe |
CN109064741A (en) * | 2018-08-01 | 2018-12-21 | 北京航空航天大学 | The method of trunk road vehicle running track reconstruct based on multisource data fusion |
EP3627472A1 (en) * | 2018-09-19 | 2020-03-25 | Deutsche Telekom AG | Method and assembly for automated local control of multi-modal urban traffic flows |
CN109348423A (en) * | 2018-11-02 | 2019-02-15 | 同济大学 | A kind of arterial road coordinate control optimization method based on sample path data |
CN109376952A (en) * | 2018-11-21 | 2019-02-22 | 深圳大学 | A kind of crowdsourcing logistics distribution paths planning method and system based on track big data |
US20220169281A1 (en) * | 2020-11-30 | 2022-06-02 | Automotive Research & Testing Center | Trajectory determination method for a vehicle |
CN115311854A (en) * | 2022-07-22 | 2022-11-08 | 东南大学 | Vehicle space-time trajectory reconstruction method based on data fusion |
CN116257797A (en) * | 2022-12-08 | 2023-06-13 | 江苏中路交通发展有限公司 | Single trip track identification method of motor vehicle based on Gaussian mixture model |
CN117473741A (en) * | 2023-10-31 | 2024-01-30 | 东南大学 | Full-sample high-resolution vehicle track robust reconstruction method, device and medium |
Non-Patent Citations (1)
Title |
---|
姚佼;戴亚轩;倪屹聆;韦钰;: "基于车辆行驶轨迹的信号交叉口排队长度估计", 公路交通科技, no. 05, 15 May 2020 (2020-05-15) * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103413444B (en) | A kind of traffic flow based on unmanned plane HD video is investigated method | |
Ban et al. | Real time queue length estimation for signalized intersections using travel times from mobile sensors | |
JP7036863B2 (en) | Systems and methods for activity monitoring using video data | |
Huang et al. | Automatic moving object extraction through a real-world variable-bandwidth network for traffic monitoring systems | |
US20150324653A1 (en) | Vehicle occupancy detection using passenger to driver feature distance | |
CN111862602A (en) | Single-intersection signal timing optimization method based on track data | |
US20220237919A1 (en) | Method, Apparatus, and Computing Device for Lane Recognition | |
CN115017742B (en) | Automatic driving test scene generation method, device, equipment and storage medium | |
CN101064061A (en) | Different species traffic information real time integrating method | |
CN112560641A (en) | Video-based one-way passenger flow information detection method in two-way passenger flow channel | |
CN114862916A (en) | Transportation vehicle tracking method and system based on ConvNeXt network and DSST algorithm | |
CN117334051B (en) | Highway vehicle track reconstruction method and system | |
CN117334051A (en) | Highway vehicle track reconstruction method and system | |
Sheng et al. | Real-time queue length estimation with trajectory reconstruction using surveillance data | |
CN112201035A (en) | Signal control intersection periodic flow estimation method driven by track data | |
CN115631082A (en) | Multi-scene path restoration method based on expressway network topological structure | |
CN110021174A (en) | A kind of vehicle flowrate calculation method for being applicable in more scenes based on video image | |
CN113674525B (en) | Signalized intersection vehicle queuing length prediction method based on sparse data | |
CN105023271A (en) | Behavior collective degree measurement method based on multi-clue information | |
CN115223144A (en) | Unmanned mine car sensor data screening method and device based on cloud data | |
Špaňhel et al. | Detection of traffic violations of road users based on convolutional neural networks | |
CN115661683A (en) | Vehicle identification statistical method based on multi-attention machine system network | |
Zhou et al. | Video driven traffic modelling | |
Jiang et al. | Real-time traffic congestion detection with SIGHTA regression network | |
Zhang et al. | Vehicle classification algorithm based on binary proximity magnetic sensors and neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant |